Artigo em revista científica Q1
Exploring events and distributed representations of text in multi-document summarization
Luís Marujo (Marujo, L.); Wang Ling (Ling, W.); Ricardo Ribeiro (Ribeiro, R.); Anatole Gershman (Gershman, A.); Jaime Carbonell (Carbonell, J.); David Martins de Matos (de Matos, D.); João Paulo Neto (Neto, J. P.); et al.
Título Revista
Knowledge-Based Systems
Ano
2016
Língua
Inglês
País
Países Baixos (Holanda)
Mais Informação
Web of Science®

N.º de citações: 17

(Última verificação: 2020-09-18 10:02)

Ver o registo na Web of Science®


: 0.9
Scopus

N.º de citações: 19

(Última verificação: 2020-09-22 13:00)

Ver o registo na Scopus


: 0.7
Abstract/Resumo
In this article, we explore an event detection framework to improve multi-document summarization. Our approach is based on a two-stage single-document method that extracts a collection of key phrases, which are then used in a centrality-as-relevance passage retrieval model. We explore how to adapt this single-document method for multi-document summarization methods that are able to use event information. The event detection method is based on Fuzzy Fingerprint, which is a supervised method trained on documents with annotated event tags. To cope with the possible usage of different terms to describe the same event, we explore distributed representations of text in the form of word embeddings, which contributed to improve the summarization results. The proposed summarization methods are based on the hierarchical combination of single-document summaries. The automatic evaluation and human study performed show that these methods improve upon current state-of-the-art multi-document summarization systems on two mainstream evaluation datasets, DUC 2007 and TAC 2009. We show a relative improvement in ROUGE-1 scores of 16% for TAC 2009 and of 17% for DUC 2007.
Agradecimentos/Acknowledgements
--
Palavras-chave
Multi-document summarization,Extractive summarization,Event detection,Distributed representations of text
  • Ciências da Computação e da Informação - Ciências Naturais
Registos de financiamentos
Referência de financiamento Entidade Financiadora
UID/CEC/50021/2013 Fundação para a Ciência e a Tecnologia
SFRH/BD/33769/2009 Fundação para a Ciência e a Tecnologia